Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning

Alshazly, Hammam; Linse, Christoph; Barth, Erhardt; Martinetz, Thomas

This paper explores how well deep learning models trained on chest CT images can diagnose COVID-19 infected people in a fast and automated process. To this end, we adopted advanced deep network architectures and proposed a transfer learning strategy using custom-sized input tailored for each deep architecture to achieve the best performance. We conducted extensive sets of experiments on two CT image datasets, namely, the SARS-CoV-2 CT-scan and the COVID19-CT. The results show superior performances for our models compared with previous studies. Our best models achieved average accuracy, precision, sensitivity, specificity, and F1-score values of [Formula: see text] , [Formula: see text] , [Formula: see text] , [Formula: see text] , and [Formula: see text] on the SARS-CoV-2 dataset, and [Formula: see text] , [Formula: see text] , [Formula: see text] , [Formula: see text] , and [Formula: see text] on the COVID19-CT dataset, respectively. For better interpretability of the results, we applied visualization techniques to provide visual explanations for the models’ predictions. Feature visualizations of the learned features show well-separated clusters representing CT images of COVID-19 and non-COVID-19 cases. Moreover, the visualizations indicate that our models are not only capable of identifying COVID-19 cases but also provide accurate localization of the COVID-19-associated regions, as indicated by well-trained radiologists.